Laboratory of Neuro Imaging, USC Mark and Mary Stevens Neuroimaging and Informatics Institute, USC Keck School of Medicine, University of Southern California, Los Angeles, California, USA.
NeuroScope Inc., New York, New York, USA.
Magn Reson Med. 2023 Jun;89(6):2419-2431. doi: 10.1002/mrm.29593. Epub 2023 Jan 24.
To develop a weakly supervised 3D perivascular spaces (PVS) segmentation model that combines the filter-based image processing algorithm and the convolutional neural network.
We present a weakly supervised learning method for PVS segmentation by combing a rule-based image processing approach Frangi filter with a canonical deep learning algorithm Unet using conditional random field theory. The weighted cross entropy loss function and the training patch selection were implemented for the optimization and to alleviate the class imbalance issue. The performance of the model was evaluated on the Human Connectome Project data.
The proposed method increases the true positive rate compared to the rule-based method and reduces the false positive rate by 36% in the weakly supervised training experiment and 39.4% in the supervised training experiment compared to Unet, which results in superior overall performance. In addition, by training the model on manually quality controlled and annotated data which includes the subjects with the presence of white matter hyperintensities, the proposed method differentiates between PVS and white matter hyperintensities, which reduces the false positive rate by 78.5% compared to weakly supervised trained model.
Combing the filter-based image processing algorithm and the convolutional neural network algorithm could improve the model's segmentation accuracy, while reducing the training dependence on the large scale annotated PVS mask data by the trained physician. Compared to the filter-based image processing algorithm, the data driven PVS segmentation model using quality-controlled data as the training target could differentiate the white matter hyperintensity from PVS resulting low false positive rate.
开发一种基于弱监督的 3D 血管周围空间（PVS）分割模型，该模型结合了基于滤波器的图像处理算法和卷积神经网络。
我们提出了一种基于弱监督的 PVS 分割学习方法，将基于规则的图像处理方法 Frangi 滤波器与基于条件随机场理论的经典深度学习算法 Unet 相结合。通过加权交叉熵损失函数和训练补丁选择来实现优化，并减轻类不平衡问题。该模型在人类连接组计划数据上进行了评估。
与基于规则的方法相比，该方法提高了真阳性率，在弱监督训练实验中降低了 36%的假阳性率，在监督训练实验中降低了 39.4%的假阳性率，优于 Unet 算法。此外，通过对包含脑白质高信号的人工质量控制和标注数据进行模型训练，该方法能够区分 PVS 和脑白质高信号，在弱监督训练模型的基础上降低了 78.5%的假阳性率。
结合基于滤波器的图像处理算法和卷积神经网络算法可以提高模型的分割准确性，同时减少对大型标注 PVS 掩模数据的训练依赖。与基于滤波器的图像处理算法相比，使用质量控制数据作为训练目标的数据驱动 PVS 分割模型可以将脑白质高信号与 PVS 区分开来，从而降低假阳性率。
